Upload model

README.md

@@ -1,50 +1,20 @@
 ---
-datasets:
-- b-mc2/sql-create-context
-language:
-- en
-library_name: transformers
-pipeline_tag: text2text-generation
-tags:
-- text-2-sql
-- text-generation-inference
+library_name: peft
 ---
-This Model is based on Llama-2 7B model provided by Meta. The Model accepts text and return SQL-query. This Model has been fine-tuned on "NousResearch/Llama-2-7b-hf".
+## Training procedure
 
-```python
-! pip install transformers accelerate
 
-# Use a pipeline as a high-level helper
-from transformers import pipeline
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+### Framework versions
 
-pipe = pipeline("text2text-generation", model="ekshat/Llama-2-7b-chat-finetune-for-text2sql")
 
-# Load model directly
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-tokenizer = AutoTokenizer.from_pretrained("ekshat/Llama-2-7b-chat-finetune-for-text2sql")
-model = AutoModelForCausalLM.from_pretrained("ekshat/Llama-2-7b-chat-finetune-for-text2sql")
-
-# Run text generation pipeline with our model
-context = "CREATE TABLE Student (name VARCHAR, college VARCHAR, age VARCHAR, group VARCHAR, marks VARCHAR)"
-question = "List the name of Students belongs to school 'St. Xavier' and having marks greater than '600'"
-
-prompt = f"""Below is an context that describes a sql query, paired with an question that provides further information. Write an answer that appropriately completes the request.
-### Context:
-{context}
-### Question:
-{question}
-### Answer:"""
-
-sequences = pipeline(
-                      prompt,
-                      do_sample=True,
-                      top_k=10,
-                      num_return_sequences=1,
-                      eos_token_id=tokenizer.eos_token_id,
-                      max_length=200,
-)
-for seq in sequences:
-  print(f"Result: {seq['generated_text']}")
-
-```
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd705fa039e2242dfbb7e123b1872f50affc63ba46e708cc9a39b0c471c01340
+size 134263757